arXiv:2509.21534v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at in-context learning, the ability to use information provided as context to improve prediction of future tokens. Induction heads have been argued to play a crucial role for in-context learning…
arXiv:2508.14134v2 Announce Type: replace Abstract: An ideal time series classification (TSC) should be able to capture invariant representations, but achieving reliable performance on out-of-distribution (OOD) data remains a core obstacle. This obstacle arises from the way models inherently entangle domain-specific…
arXiv:2509.21545v1 Announce Type: new Abstract: The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce…
arXiv:2411.19368v2 Announce Type: replace-cross Abstract: Constructing valid confidence sets is a crucial task in statistical inference, yet traditional methods often face challenges when dealing with complex models or limited observed sample sizes. These challenges are frequently encountered in modern applications,…
arXiv:2503.13562v3 Announce Type: replace Abstract: In real-world applications, it is highly challenging to detect anomalous samples with extremely sparse anomalies, as they are highly similar to and thus easily confused with normal samples. Moreover, the number of anomalous samples is…
arXiv:2509.00472v2 Announce Type: replace Abstract: Causal inference in settings involving complex spatio-temporal dependencies, such as environmental epidemiology, is challenging due to the presence of unmeasured confounding. However, a significant gap persists in existing methods: current diffusion-based causal models rely on…
arXiv:2509.22196v1 Announce Type: cross Abstract: Disentangled representations seek to recover latent factors of variation underlying observed data, yet their identifiability is still not fully understood. We introduce a unified framework in which disentanglement is achieved through mechanistic independence, which characterizes…
arXiv:2509.22501v1 Announce Type: cross Abstract: Non-stationary extremal dependence, whereby the relationship between the extremes of multiple variables evolves over time, is commonly observed in many environmental and financial data sets. However, most multivariate extreme value models are only suited to…
arXiv:2509.21940v1 Announce Type: new Abstract: In this paper, we study the problem of distributed mean estimation with 1-bit communication constraints. We propose a mean estimator that is based on (randomized and sequentially-chosen) interval queries, whose 1-bit outcome indicates whether the…
arXiv:2509.21572v1 Announce Type: new Abstract: Sparse Bayesian learning (SBL) associates to each weight in the underlying linear model a hyperparameter by assuming that each weight is Gaussian distributed with zero mean and precision (inverse variance) equal to its associated hyperparameter.…
